AU2017327430B2 - Monitoring infrastructure facilities by means of geo-clustering - Google Patents
Monitoring infrastructure facilities by means of geo-clustering Download PDFInfo
- Publication number
- AU2017327430B2 AU2017327430B2 AU2017327430A AU2017327430A AU2017327430B2 AU 2017327430 B2 AU2017327430 B2 AU 2017327430B2 AU 2017327430 A AU2017327430 A AU 2017327430A AU 2017327430 A AU2017327430 A AU 2017327430A AU 2017327430 B2 AU2017327430 B2 AU 2017327430B2
- Authority
- AU
- Australia
- Prior art keywords
- operating state
- predefined operating
- predefined
- vehicles
- messages
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 11
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000011156 evaluation Methods 0.000 claims abstract description 17
- 238000004590 computer program Methods 0.000 claims abstract description 5
- 230000008878 coupling Effects 0.000 claims description 5
- 238000010168 coupling process Methods 0.000 claims description 5
- 238000005859 coupling reaction Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 230000036461 convulsion Effects 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 238000005461 lubrication Methods 0.000 claims description 3
- 239000004576 sand Substances 0.000 claims description 3
- 238000005259 measurement Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 6
- 230000003137 locomotive effect Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 4
- 239000003086 colorant Substances 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/40—Handling position reports or trackside vehicle data
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/50—Trackside diagnosis or maintenance, e.g. software upgrades
- B61L27/53—Trackside diagnosis or maintenance, e.g. software upgrades for trackside elements or systems, e.g. trackside supervision of trackside control system conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61L—GUIDING RAILWAY TRAFFIC; ENSURING THE SAFETY OF RAILWAY TRAFFIC
- B61L27/00—Central railway traffic control systems; Trackside control; Communication systems specially adapted therefor
- B61L27/50—Trackside diagnosis or maintenance, e.g. software upgrades
- B61L27/57—Trackside diagnosis or maintenance, e.g. software upgrades for vehicles or trains, e.g. trackside supervision of train conditions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
- Train Traffic Observation, Control, And Security (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to a method and to a computer program product for carrying out the method for monitoring infrastructure facilities of a route network for vehicles, which vehicles generate messages about the respective operating state, which messages are transmitted with a time and a specification of location which represent the occurrence of the signal operating state, connected to a land-based evaluation device, which messages are received by the land-based evaluation device stored in a database and evaluated, characterized by the following method steps: reading out the messages of a predefined time period relating to at least one predefined operating state from the database; determining limited areas with frequent occurrence of the predefined operating state by means of a predefined algorithm; detecting the infrastructure facilities in the areas with the frequent occurrence of the predefined operating state as a possible cause of the predefined operating state of the vehicles, and outputting information about the infrastructure facilities which are detected as a possible cause of the predefined operating state of the vehicles.
Description
Description
MONITORING INFRASTRUCTURE FACILITIES BY MEANS OF GEO-CLUSTERING
The invention relates to a method and a computer program product for executing said method for monitoring infrastructure facilities of a route network for vehicles, which vehicles generate messages about their respective operating state, which messages are transmitted with an associated time and location specification that represent the occurrence of the signaled operating state to a land-based evaluation device, which messages are received by the land-based evaluation device, stored in a database and evaluated.
Incidents or faults of a technical nature in the operation of vehicles, for example rail vehicles, can have a variety of causes. For example, an unintentional lowering of a pantograph (dropping) can be attributed to too low a contact force, which represents a malfunction of the rail vehicle itself, or can be caused by events external to the vehicle, for example due to an incorrect transition point between two interconnected individual cables of the overhead line. Also, the causes for excessive sparking or spinning of driven wheels can be found both in the vehicle itself and in infrastructure facilities.
A prerequisite for minimizing these technical incidents thus involves knowledge of the causes of the technical incidents, without which the faults cannot be rectified. If the accidental lowering of a pantograph is due to the vehicle itself, the vehicle would need to be checked. Correspondingly, in the other case the overhead line would need to be checked at the appropriate position.
Without detailed knowledge of the causes, both the vehicle as well as the route network would need to be checked.
2017327430 10 Oct 2019
Both of these are currently performed by visual inspections, which leads to the vehicle being taken out of service for the time required to test and possibly repair it, and to closure of the appropriate section of the route network for the time required for testing and, where necessary, repair.
It is an object of the present invention to substantially overcome or at least ameliorate one or more of the above disadvantages.
Aspects of the present disclosure increase the technical availability of vehicles and the route network and at the same time, to significantly reduce their operating costs.
A method according to the invention for monitoring infrastructure facilities of a route network for vehicles, which vehicles generate messages about their respective operating state, which messages are transmitted with an associated time and location specification that represent the occurrence of the signaled operating state to a land-based evaluation device, and which are received by the land-based evaluation device, stored in a database and evaluated, the method comprising the following method steps:
- reading out the messages of a predefined time period relating to at least one predefined operating state from the database;
- determining limited areas with frequent occurrence of the predefined operating state by means of an automatic segmentation algorithm by grouping the location specifications;
- identifying the infrastructure facilities in the areas having the frequent occurrence of the predefined operating state as a possible cause of the predefined operating state of the vehicles, and
- - outputting information about the infrastructure facilities that are identified as a possible cause of the predefined operating state of the vehicles.
23550496 (IRN: P0005667AU)
PCT/EP2017/072292
016P19511W0US
The method according to the invention is advantageously a computer-implemented method, and therefore exists in the form of software and can be easily stored on a storage medium, transported and loaded therefrom back into a processing unit. This is referred to as a computer program product (data carrier with code), which, if loaded into a computer, causes the method according to the invention to be executed. The evaluation device therefore comprises both means for reading the storage medium with the computer-implemented methods that are stored on and can be read from said medium, as well as a processing unit which is suitably designed for executing the computerimplemented method.
In addition to the identification of limited areas with frequent occurrence, this also allows areas with isolated occurrences of the predefined operating state to be determined. An extension of the invention thus consists of
- identifying the vehicles in, in particular limited, areas with isolated occurrence of the predefined operating state as a possible cause of the predefined operating state of the vehicles and
- outputting information about the infrastructure facilities that are identified as a possible cause of the predefined operating state of the vehicles.
The areas of isolated occurrence of the predefined operating state are different to the areas of frequent occurrence and are therefore located outside of these. The following considerations, in particular relating to determining the causes or to outputting the causes, to the limited areas of frequent occurrence of the predefined operating state are also intended to apply to the areas of occasional occurrence of the predefined operating state.
PCT/EP2017/072292
016P19511W0US
The vehicles are in particular rail vehicles. The route network is then a route network for rail vehicles. It comprises infrastructure facilities such as tracks with rails and sets of points, signaling systems or contact lines, mostly implemented as overhead cables or busbars. In accordance with an extension of the method according to the invention, this is therefore used for monitoring infrastructure facilities of a route network for rail vehicles.
The messages are generated on the vehicles and transmitted to at least one land-based evaluation device, for example by wireless means. To this end, each vehicle has at least one transmitting device and the at least one land-based evaluation device has at least one receiving device. The messages comprise data relating to a current operating state in a predefined form, so that they can be evaluated by the land-based evaluation device. The land-based evaluation device, as indicated above, is therefore suitably designed. In addition, the messages comprise at least the time and location of the occurrence of the reported operating state in a predefined form, for example, the location is specified using GPS coordinates or by means of other satellite navigation data, such as GPS, GLONASS, Galileo, BEIDOU etc.
First of all, the messages stored in the database relating to one or more predefined operating states, which were generated within a specified period of time, are read out. It is also possible for all messages from the time interval to be read out and then further processed after being grouped according to the predefined operating states or sorted according to the individual operating states.
In order to determine limited areas with frequent occurrence of the predefined operating state and so ultimately to identify the infrastructure facilities located at the locations or in the areas of the frequent occurrence of the predefined
PCT/EP2017/072292
016P19511W0US
- 5 operating states as a possible operating state of the vehicles, used.
cause of the predefined a predefined algorithm is
On the one hand, the limited areas can be delimited from each other and therefore do not overlap each other. On the other hand, their respective size and thus their planar extension can be narrowly defined - in that case, compared to the total area of an entire area under consideration, which includes all infrastructure facilities to be monitored and in which all messages to be evaluated relating to the predefined operating state have occurred, they are relatively small. The limited areas can also be chosen to be the same size.
In an extension, the limited areas with frequent occurrence of the predefined operating state are determined by means of a predefined algorithm, in particular an automatic segmentation algorithm, by grouping the location specifications. A limited area with multiple occurrence of the at least one predefined operating state can also be referred to as a cluster. Therefore, the terms clustering or geo-clustering are also appropriate here.
A number of different suitable algorithms have become known, in particular, so-called cluster analyses, in particular from the field of machine learning (machine learning clustering methods). Automatic segmentation algorithms from the field of unsupervised learning are used to discover patterns or similarity structures in (large) datasets, which differ from the unstructured noise.
In accordance with another extension the limited areas with frequent occurrence of the predefined operating state are determined by means of a k-means algorithm.
PCT/EP2017/072292
016P19511W0US
In the application of the k-means algorithm a number of possible limited areas are defined within an overall area. In an extended form, this number of possible limited areas within the overall area is defined as a function of the size or the planar extension of the overall area and as a function of the predefined operating state. In a further extension, a very large number of possible limited areas is defined within the overall area, so that sporadic individual cases can each be assigned to their own limited area, so that these are subsequently filtered out as noise rather than being assigned to the nearest area. In this way, for example, on a total area of 100,000 km2, 10,000 possible areas can be defined, so that each limited area covers only 10 km2. Depending on the number of the infrastructure facilities to be monitored, such as the number of sets of points, in the overall area or even according to their cumulative arrangement in the overall area, for example in the area of stations or depots, the limited areas can be chosen to be smaller or larger.
As an alternative to the k-means algorithm a DBSCAN algorithm can be used to identify locations with frequent occurrence of the predefined operating state. DBSCAN stands for Density-Based Spatial Clustering of Applications with Noise ([German translation]). This algorithm operates mainly with a predefined parameter, namely the maximum distance between the locations of the occurrence of the predefined operating states in the same limited area. In order to determine the limited areas with frequent occurrence of the predefined operating state by means of the DBSCAN algorithm, the method is extended such that a maximum distance between the locations of the occurrence of the predefined operating states in the same limited area is specified as a function of the predefined operating state. Here, too, depending on the infrastructure facility to be monitored - and thus as a function of the predefined operating state of the vehicle - the maximum distance can be selected. Thus, for example for monitoring overhead lines or points, a
PCT/EP2017/072292
016P19511W0US maximum distance of 100m can be specified. In addition to the maximum distance, in the determination of the limited areas using the DBSCAN algorithm a further parameter can be specified, namely the minimum number of neighbors to be reached. This parameter is used to define when an isolated occurrence of the predefined operating state exists and it is typically set to z > 1, for example, to z = 3.
Other algorithms are possible and typically come from, for example, the group known as Gaussian Mixture Models (GMM).
A further development of the invention involves the idea that to determine the limited areas with frequent occurrence of the predefined operating state by means of the predefined algorithm, messages relating to the predefined operating state of vehicles on identical journeys are exclusively taken into account. This can be carried out in practice as a filtering operation following the above-described segmentation using the k-means or DBSCAN algorithm. As already described above, in order to reduce the number of the limited areas to be filtered, depending on the occurrence of the predefined operating state, in the case of the DBSCAN algorithm the minimum number of neighbors to be reached can be increased.
Thus, two messages from one and the same vehicle in a limited area are only taken into account once, unless there is a very long time, typically several hours or a day, specified between them. The vehicle must have either moved in the meantime, or it must have been de-equipped and re-equipped. In the case of a two-directional vehicle, the reversal of the direction of travel of the vehicle could also have the same effect. In an extension, to determine limited areas with frequent occurrence of the predefined operating state by means of the predefined algorithm, messages relating to the predefined operating state of non-identical vehicles are exclusively taken into account. The non-identical vehicles are not necessarily differently
PCT/EP2017/072292 -82 016P19511W0US equipped. Vehicles of the same type can be designed to be completely identical in all technically relevant features. However, this must not involve the same vehicle which has generated and transmitted two messages relating to the predefined operating state at the same place, or in the same limited area, at two different times within the period under consideration.
The specification of the above-mentioned parameters, for example, the specification of a number of possible limited areas within an overall area of the messages relating to the predefined operating state or the maximum distance between the locations of the occurrence of the predefined operating states in the same limited area, can be carried out by the user. In an extension, all parameters for determining the limited areas with frequent occurrence of the predefined operating state using the predefined algorithm can be specified by a user.
Additionally or alternatively, the output of information can be controlled by a user. The user can specify, for example, threshold values that must be exceeded or undershot, so that information can be output to the user. Threshold values can relate to the number x of messages relating to the predefined operating state of vehicles on non-identical journeys and/or a number y of messages relating to the predefined operating state in a limited area with frequent occurrence of the predefined operating state. If, for example, in a first limited area with frequent occurrence of the predefined operating state three messages exist relating to the predefined operating state of vehicles on non-identical journeys and in a second limited area there are five, and if the corresponding threshold is then set to at least four, only the second area, or the infrastructure facilities located in the second area, are output as a possible cause of the predefined operating state of the vehicles.
PCT/EP2017/072292
016P19511W0US
Thus, for example, the determination of the limited areas with frequent occurrence of the predefined operating state using the specified algorithm, or at least the output of information about the infrastructure facilities identified as a possible cause of the predefined operating state of the vehicles, can in future be carried out as a function of a specified relative frequency of the messages relating to the at least one predefined operating state in the predefined possible limited areas with frequent occurrence of the predefined operating state relative to a total number of messages relating to the at least one specified operating condition that are read out of the database and processed using the predefined algorithm. Thus, it is possible to only output clusters with a high relative number, such as 1-10% of the total number of messages relating to the at least one predefined operating state.
Both the evaluation unit and the computer program product must of course be suitably designed.
The information about the limited areas with the infrastructure facilities identified as a possible cause of the predefined operating state of the vehicles, or directly about the infrastructure facilities thus identified, can, in turn, be output in the form of messages, for example via a screen in the evaluation device.
In addition to the information output about the limited areas with the infrastructure facilities identified as a possible cause of the predefined operating state of the vehicles or about the infrastructure facilities identified as a possible cause of the predefined operating state of the vehicles, information can be output relating to
- a total number of messages read out of the database and processed by means of the predefined algorithm, relating to the at least one predefined operating state and/or to
PCT/EP2017/072292
016P19511W0US
- a respective absolute number of messages relating to the at least one predefined operating state in the areas with frequent occurrence of the predefined operating state and/or relating to
- a respective relative frequency of the messages relating to the at least one predefined operating state in the areas with frequent occurrence of the predefined operating state relative to the total number of messages read out of the database and processed by means of the predefined algorithm, relating to the at least one predefined operating state, and/or relating to
- a respective number of messages relating to the at least one predefined operating state of non-identical vehicles and/or of vehicles on non-identical journeys in the areas with frequent occurrence of the predefined operating state, and/or relating to
- a respective number of messages relating to the at least one predefined operating state of non-identical vehicles or of vehicles on non-identical journeys in the areas with frequent occurrence of the predefined operating state, and/or relating to
- a respective relative frequency of messages relating to the at least one predefined operating state of nonidentical vehicles or of vehicles on non-identical journeys in the areas with frequent occurrence of the predefined operating state relative to the total number of messages read out of the database and processed by means of the predefined algorithm relating to the at least one predefined operating state and/or relating to
- a respective planar extension of the limited areas with frequent occurrence of the predefined operating state and/or to
PCT/EP2017/072292
016P19511W0US
- a number of possible limited areas within an entire area of the messages relating to the predefined operating state and/or to
- the algorithm for determining the limited areas with frequent occurrence of the predefined operating state and/or to
- the specified parameters of the algorithm for determining the limited areas with frequent occurrence of the predefined operating state and/or to
- the predefined operating state.
In particular, the individual limited areas with frequent occurrence of the predefined operating state can be classified into ranked lists according to different criteria, for example, according to
- the respective absolute number of messages relating to the at least one predefined operating state in the areas with frequent occurrence of the predefined operating state and/or according to
- the respective relative frequency of the messages relating to the at least one predefined operating state in the areas with frequent occurrence of the predefined operating state relative to the total number of messages relating to the at least one predefined operating state that are read out of the database and processed using the predefined algorithm, and/or according to
- the respective number of messages relating to the at one predefined operating state of non-identical vehicles and or of vehicles on non-identical journeys in the areas with frequent occurrence of the predefined operating state .
In an extension, a ranked list of the areas with frequent occurrence of the predefined operating state is created and is output as a function of
PCT/EP2017/072292 - ΙΣΣΟ 1 6P1 95 1 1W0US
- a respective number of the messages relating to the at least one predefined operating state, in particular from non-identical vehicles or from vehicles on non-identical journeys, in the areas with frequent occurrence of the predefined operating state, and/or of
- a respective planar extension of the limited areas with frequent occurrence of the predefined operating state.
Thus, the significance of the limited areas with frequent occurrence of the predefined operating state is determined by means of a predefined algorithm and output in a ranked list, for example, displayed on a screen. The limited areas can be displayed on a map, for example in the form of circles. The colors of the circles can reflect the predefined operating state. The sizes of the circles, in turn, can be used in a similar way to sketch the relative frequency of messages relating to the predefined operating state in the limited area.
A further advantageous development of the invention is that further messages relating to the at least one predefined operating state, which are associated with a time that represents the occurrence of the signaled operating state, which occurs after the specified period of time, are processed with the predefined algorithm without reading out of the database and processing the messages from the specified time period relating to at least one predefined operating state once again .
To this end, at least one additional message relating to the at least one predefined operating state is read out of the database after the specified period, and using the predefined algorithm it is determined whether the at least one additional message must be assigned to a limited area with frequent occurrence of the predefined operating state.
PCT/EP2017/072292
016P19511W0US
Then - if the at least one additional message must be assigned to a limited area with frequent occurrence of the predefined operating state - the limited areas of the frequent occurrence of the predefined operating state, or the infrastructure facilities located in the limited areas, are again identified as a possible cause of the predefined operating state of the vehicles, and information about the limited areas of the frequent occurrence of the predefined operating state or about the infrastructure facilities identified as a possible cause of the predefined operating state of the vehicles are output. Otherwise, this would be an isolated occurrence and the vehicle would be output as the cause.
According to the algorithm used, the processing of the messages after the specified time period and thus the determination of the limited areas with frequent occurrence of the predefined operating state proceed in different ways.
Thus, for example, it can be determined whether the message was generated at a location which is in a limited area with frequent occurrence of the predefined operating state, to which limited area thus at least two or more messages from the specified period were assigned. If only a single message from the specified time period was assigned to the limited area, then this previously involved an isolated occurrence. Depending on the criterion, the limited area following the assignment of the additional message relating to this limited area can be identified and output as a limited area with frequent occurrence of the predefined operating state. An alternative consists in the fact that the distances of the location of the additional message to the nearest locations of the messages from the specified time period are calculated and it is then determined whether these should be assigned to an existing cluster, whether a new cluster is detected or whether an isolated occurrence of the predefined operating state is involved.
PCT/EP2017/072292
016P19511W0US
Of course, this changes the total number of messages read out from the database and processed by means of the predefined algorithm and the corresponding relative frequencies. In an extended form this is appropriately taken into account.
As already explained above, a further extension of the invention consists in the fact that the method for monitoring infrastructure facilities of a route network is designed for rail vehicles. In an extension, the at least one predefined operating state relates to
- an unplanned lowering of a pantograph of the rail vehicles,
- an unplanned shutdown of a power system of the rail vehicles,
- a distribution of sand by the rail vehicles,
- an oil lubrication of the rails by means of the rail vehicles,
- a failed coupling operation of the rail vehicles,
- door opening errors of the rail vehicles,
- the violation of a specified jerk value of the rail vehicles,
- rapid braking actions of the rail vehicles and/or
- communication errors of the rail vehicles with a control center.
A unplanned lowering of a current collector, also known as a pantograph, is lowered by the train's self-protection system, for example if the pantograph receives an external impact, in particular from the overhead line as an infrastructure facility, or if the contact force is too low. An unplanned shutdown of a power system, in particular of locomotives, occurs for example, if the monitoring of the input voltage and input current into the locomotive shows an overvoltage or if the locomotive detects a short circuit or ground fault or if no stable voltage is supplied on a specific AC-current frequency
PCT/EP2017/072292
016P19511W0US band (50Hz/100Hz protection). A sand distribution on the track - also known as sanding of the rails - takes place, for example, if the track is contaminated with dirt at certain points, typically at level crossings, so that the respective rail vehicle, such as a locomotive, slips off the track (sliding skid protection) . An oil-lubrication of the rails is carried out by means of the rail vehicles, for example, if the locomotive has too high a starting resistance. Failed coupling operations, for example, with other rail vehicles or with other parts of the same rail vehicle, in particular with other carriages or locomotives occur, for example, if the coupling has to be performed in a tight curve or due to a user error, for example, a sticking ignition key, which can occur at several places. Violations of a predefined jerk value, thus impacts due to high acceleration value outliers, occur for example, when goods wagons are moved together too violently during a coupling operation or due to poor-quality rail sections, such as uneven sections or warped rails. Also, rapid braking operations are typically caused by the train protection system, for example, in the event of a defective safety balise or due to external influences, such as a radar system nearby. Door opening faults occur, for example, due to uneven platform edges. Communication errors occur frequently when the radio connection to the train control station is interrupted (radio holes).
In an extension, the message about the respective operating state of the vehicle, which represents the occurrence of the signaled operating state, can also comprise one or more measurement values of at least one measurement variable or be formed by one or more measurement values of at least one measurement variable. In that case the vehicle comprises at least one measurement device for recording measurement values of at least one measurement variable. A message relating to a predefined operating state, in particular, for example, an
PCT/EP2017/072292
016P19511W0US error message, is only generated if at least one measurement value lies outside of a specified operating range.
Using the method, in addition to the limited areas it is also possible to detect a specific vehicle from the group of vehicles in which a predefined operating state frequently occurs :
- identifying vehicles with frequent occurrence of the predefined operating state outside of the limited areas of the frequent occurrence of the predefined operating state by means of a predefined algorithm;
- identifying the vehicles of the frequent occurrence of the predefined operating state outside of the limited areas of the frequent occurrence of the predefined operating state as a possible cause of the predefined operating state of the vehicles, and
- outputting information about the vehicles that are identified as a possible cause of the predefined operating state of the vehicles.
This also rules out the possibility that the occurrence takes place on the infrastructure facilities identified as a possible cause of the predefined operating state of the vehicles.
The invention allows numerous embodiments. It will be explained on the basis of the following figures, each of which shows an exemplary embodiment. Identical elements in the figures are labelled with the same reference numerals.
The figure shows a section of the screen (screenshot) with an excerpt of a map having a plurality of infrastructure facilities of a route network for rail vehicles, which is displayed on a screen of a land-based evaluation device. Multiple rail vehicles are travelling on this route network, in particular independently of each other, and generate messages relating to their respective operating states. These are
PCT/EP2017/072292
016P19511W0US assigned a time stamp and a location specification and are sent to the land-based evaluation device, received thereby, stored in a data base sorted in accordance with the signaled operating states and evaluated by means of a predefined algorithm in order to monitor the route network.
For this purpose, the messages relating to at least one predefined operating state, which were generated within a specified interval, are read out of the database. Messages relating to a plurality of operating states, which are assigned to a predefined category or a group of predefined operating states, for example having a certain similarity, are read out and further processed collectively. The messages are then grouped according to the locations of their occurrence and limited areas with frequent occurrence of the predefined operating state are determined and output by displaying them on the map .
Here, a plurality of circles on the map illustrate the limited areas with frequent occurrence of the predefined operating states. The operating states can be selected by the user from a list on the left-hand side. Here, an accidental lowering of a pantograph was defined as the operating state. Multiple operating states can also be selected. These are in turn represented by their colors. A first limited area with frequent occurrence of a first specified operating state is marked with a circle of a first color, while a second limited area with frequent occurrence of a second specified operating state is marked with a circle of a second color, wherein the first color is different from the second color.
The sizes of the circles can be used in a similar way to indicate the relative frequency of the messages relating to the predefined operating state in the limited area.
PCT/EP2017/072292
016P19511W0US
The user can select when a limited area should be imaged at all, thus the relative frequency of messages relating to the predefined operating state that must occur at the very least in the limited areas to be output in order to display them. Here, this value is 1% of the total number of stored and evaluated messages but can be increased up to 10%. In this case, here only messages of vehicles on non-identical journeys are taken into account. Here, at least two messages exist from vehicles on non-identical journeys in the limited area, so that the limited area is displayed. This specification must also be specified and, if appropriate, varied by the user.
The output here is provided to the operator of the infrastructure facility for planning maintenance.
Further outputs can be: the total number of messages, the number of messages in the respective identified area of frequent occurrence of the predefined operating state, the number of vehicles in the period under consideration in the respective identified area of the frequent occurrence of the predefined operating state, in particular those which have also generated at least one message relating to their respective (arbitrary) operating state in the area concerned, as well as the relative frequency of the messages relating to the at least one predefined operating state in the respective area with frequent occurrence of the predefined operating state relative to the total number of messages read out of the database relating to the at least one predefined operating state.
Claims (14)
- CLAIMS:1. A method for monitoring infrastructure facilities of a route network for vehicles, which vehicles generate messages about their respective operating state, which messages are transmitted with an associated time and location specification that represent the occurrence of the signaled operating state, to a land-based evaluation device, which messages are received by the land-based evaluation device, stored in a database and evaluated, the method comprising following method steps:- reading out the messages of a predefined time period relating to at least one predefined operating state from the database;- determining limited areas with frequent occurrence of the predefined operating state by means of an automatic segmentation algorithm by grouping the location specifications;- identifying the infrastructure facilities in the areas having the frequent occurrence of the predefined operating state as a possible cause of the predefined operating state of the vehicles, and- outputting information about the infrastructure facilities which are identified as a possible cause of the predefined operating state of the vehicles.
- 2. The method as claimed in claim 1, further comprising the following method steps:- identifying the vehicles in the areas with isolated occurrence of the predefined operating state as a possible cause of the predefined operating state of the vehicles, and- outputting information about the vehicles that are identified as a possible cause of the predefined operating state of the vehicles.
- 3. The method as claimed in any one of claims 1 or 2, further comprising the following method steps:- reading out at least one additional message which relates to the at least one predefined operating state from the database, which message is associated with a time that represents the occurrence of the signaled operating state, which follows the specified time period;- using a predefined algorithm to determine whether the at least one additional message should be assigned to a limited area having frequent occurrence of the predefined operating23550496 (IRN: P0005667AU)2017327430 10 Oct 2019 state, and if the at least one additional message should be assigned to a limited area with frequent occurrence of the predefined operating state,- identifying the infrastructure facilities of the limited area having the frequent occurrence of the predefined operating state as a possible cause of the predefined operating state of the vehicles, and- outputting at least one information item about the infrastructure facilities that are identified as a possible cause of the predefined operating state of the vehicles.
- 4. The method as claimed in any one of claims 1 to 3, wherein to determine limited areas with frequent occurrence of the predefined operating state by means of the predefined algorithm, messages relating to the predefined operating state of vehicles on non-identical journeys are exclusively taken into account.
- 5. Method according to any one of claims 1 to 4, wherein the limited areas with frequent occurrence of the predefined operating state are determined by means of a k-means algorithm.
- 6. The method as claimed in claim 5, wherein a number of possible limited areas within an entire area is defined as a function of the entire area and as a function of the predefined operating state.
- 7. Method according to any one of Claims 1 to 4, wherein the limited areas with frequent occurrence of the predefined operating state are determined by means of a DBSCAN algorithm.
- 8. The method as claimed in claim 7, wherein a maximum distance between the locations of the occurrence of the predefined operating states is defined as a function of the predefined operating state.23550496 (IRN: P0005667AU)2017327430 10 Oct 2019
- 9. The method as claimed in any one of claims 1 to 8, wherein information is output relating to- a total number of messages read out of the database relating to the at least one predefined operating state and/or to- a respective number of messages relating to the at least one predefined operating state in the areas with frequent occurrence of the predefined operating state and/or relating to- a respective relative frequency of the messages relating to the at least one predefined operating state in the areas with frequent occurrence of the predefined operating state relative to the total number of messages read out of the database relating to the at least one predefined operating state, and/or relating to- a respective number of messages relating to the at least one predefined operating state of non-identical vehicles or of vehicles on non-identical journeys in the areas with frequent occurrence of the predefined operating state, and/or relating to- a respective relative frequency of messages relating to the at least one predefined operating state of non-identical vehicles or of vehicles on non-identical journeys in the areas with frequent occurrence of the predefined operating state relative to the total number of messages read out of the database that relate to the at least one predefined operating state and/or relating to- a respective extension of the limited areas with frequent occurrence of the predefined operating state and/or to- a number of possible limited areas within an entire area of the messages relating to the predefined operating state and/or to- the algorithm for determining the limited areas with frequent occurrence of the predefined operating state and/or to- the predefined operating state.
- 10. The method as claimed in any one of claims 1 to 9, wherein a ranked list of the areas with frequent occurrence of the predefined operating state is created and is output as a function of23550496 (IRN: P0005667AU)2017327430 10 Oct 2019- a respective number of messages relating to the at least one predefined operating state;- a respective extension of the limited areas with frequent occurrence of the predefined operating state and- a respective relative frequency of the messages relating to the at least one predefined operating state in the areas with frequent occurrence of the predefined operating state relative to a total number of messages read out of the database relating to the at least one predefined operating state.
- 11. The method as claimed in any one of claims 1 to 10, wherein the determination of the limited areas with frequent occurrence of the predefined operating state by means of the predefined algorithm, or at least the output of information about the infrastructure facilities identified as a possible cause of the predefined operating state of the vehicles, is carried out as a function of:- a predefined relative frequency of the messages relating to the at least one predefined operating state in the specified possible limited areas with frequent occurrence of the predefined operating state relative to a total number of messages read out of the database relating to the at least one predefined operating state.
- 12. The method as claimed in claim 11, wherein the number of possible limited areas with frequent occurrence of the predefined operating state within the entire area of the messages relating to the predefined operating state and the fact that the relative frequency of the messages relating to the at least one predefined operating state in the specified possible limited areas with frequent occurrence of the predefined operating state relative to the total number of messages read out of the database relating to the at least one predefined operating state are specified by a user.
- 13. The method as claimed in any one of claims 1 to 12, wherein it is used for monitoring infrastructure facilities of a route network for rail vehicles, wherein the at least one predefined operating state relates to an unplanned lowering of a23550496 (IRN: P0005667AU)2017327430 10 Oct 2019 pantograph of the rail vehicles and/or wherein the at least one predefined operating state relates to an unplanned shutdown of a power system of the rail vehicles and/or wherein the at least one predefined operating state relates to a distribution of sand by the rail vehicles and/or wherein the at least one predefined operating state relates to an oil lubrication of the rails by the rail vehicle and/or wherein the at least one predefined operating state relates to a failed coupling operation of the rail vehicles and/or wherein the at least one predefined operating state relates to door faults of the rail vehicles and/or wherein the at least one predefined operating state relates to the exceeding of a predefined jerk value of the rail vehicles and/or wherein the at least one predefined operating state relates to rapid braking operations of the rail vehicles and/or wherein the at least one predefined operating state relates to communication errors of the rail vehicles with a control center.
- 14. A computer program product for executing the method as claimed in any of claims 1 to 13.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| DE102016217883.0A DE102016217883A1 (en) | 2016-09-19 | 2016-09-19 | Monitoring of infrastructure facilities by means of geoclustering |
| DE102016217883.0 | 2016-09-19 | ||
| PCT/EP2017/072292 WO2018050502A1 (en) | 2016-09-19 | 2017-09-06 | Monitoring infrastructure facilities by means of geo-clustering |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| AU2017327430A1 AU2017327430A1 (en) | 2019-03-28 |
| AU2017327430B2 true AU2017327430B2 (en) | 2020-03-19 |
Family
ID=59955533
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| AU2017327430A Active AU2017327430B2 (en) | 2016-09-19 | 2017-09-06 | Monitoring infrastructure facilities by means of geo-clustering |
Country Status (7)
| Country | Link |
|---|---|
| US (1) | US11299185B2 (en) |
| EP (1) | EP3487748B1 (en) |
| AU (1) | AU2017327430B2 (en) |
| DE (1) | DE102016217883A1 (en) |
| ES (1) | ES2922052T3 (en) |
| RU (1) | RU2722370C1 (en) |
| WO (1) | WO2018050502A1 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11232115B2 (en) * | 2018-04-11 | 2022-01-25 | Nokia Technologies Oy | Identifying functional zones within a geographic region |
| US11260888B2 (en) * | 2018-11-16 | 2022-03-01 | Alstom Transport Technologies | Method and system for health assessment of a track circuit and/or of a track section |
| CN110795510B (en) * | 2019-10-22 | 2023-05-23 | 北京空间技术研制试验中心 | Spacecraft system health state evaluation method based on high-dimensional data association mining |
| US11605286B1 (en) * | 2021-10-22 | 2023-03-14 | X Development Llc | Alert generation algorithm for tracking devices |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1900597A1 (en) * | 2006-09-18 | 2008-03-19 | Bombardier Transportation GmbH | Diagnostic system and method for monitoring a rail system |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7819003B2 (en) * | 2002-06-11 | 2010-10-26 | Intelligent Technologies International, Inc. | Remote monitoring of fluid storage tanks |
| US8047432B2 (en) * | 2002-06-11 | 2011-11-01 | Intelligent Technologies International, Inc. | Package tracking techniques |
| US20080270076A1 (en) * | 2002-06-11 | 2008-10-30 | Intelligent Technologies International, Inc. | Remote Monitoring of Operating Parts of Assets |
| US20080177678A1 (en) * | 2007-01-24 | 2008-07-24 | Paul Di Martini | Method of communicating between a utility and its customer locations |
| US8412393B2 (en) | 2008-07-01 | 2013-04-02 | General Electric Company | Apparatus and method for monitoring of infrastructure condition |
| US20100142447A1 (en) * | 2008-09-04 | 2010-06-10 | Ludger Schlicht | Web applications for a mobile, broadband, routable internet |
| JP5110405B2 (en) | 2010-04-07 | 2012-12-26 | 村田機械株式会社 | Traveling cart system |
| EP2937241B1 (en) * | 2014-04-24 | 2017-03-08 | Hitachi, Ltd. | Railway vehicle damage estimation |
| US9487222B2 (en) | 2015-01-08 | 2016-11-08 | Smartdrive Systems, Inc. | System and method for aggregation display and analysis of rail vehicle event information |
| US9902410B2 (en) | 2015-01-08 | 2018-02-27 | Smartdrive Systems, Inc. | System and method for synthesizing rail vehicle event information |
| US9296401B1 (en) * | 2015-01-12 | 2016-03-29 | Smartdrive Systems, Inc. | Rail vehicle event triggering system and method |
| US11774944B2 (en) * | 2016-05-09 | 2023-10-03 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for the industrial internet of things |
| US11156998B2 (en) * | 2016-05-09 | 2021-10-26 | Strong Force Iot Portfolio 2016, Llc | Methods and systems for process adjustments in an internet of things chemical production process |
-
2016
- 2016-09-19 DE DE102016217883.0A patent/DE102016217883A1/en not_active Withdrawn
-
2017
- 2017-09-06 US US16/334,444 patent/US11299185B2/en active Active
- 2017-09-06 WO PCT/EP2017/072292 patent/WO2018050502A1/en unknown
- 2017-09-06 ES ES17771993T patent/ES2922052T3/en active Active
- 2017-09-06 AU AU2017327430A patent/AU2017327430B2/en active Active
- 2017-09-06 RU RU2019111672A patent/RU2722370C1/en active
- 2017-09-06 EP EP17771993.7A patent/EP3487748B1/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1900597A1 (en) * | 2006-09-18 | 2008-03-19 | Bombardier Transportation GmbH | Diagnostic system and method for monitoring a rail system |
Also Published As
| Publication number | Publication date |
|---|---|
| US20190210623A1 (en) | 2019-07-11 |
| EP3487748B1 (en) | 2022-04-20 |
| DE102016217883A1 (en) | 2018-03-22 |
| AU2017327430A1 (en) | 2019-03-28 |
| ES2922052T3 (en) | 2022-09-07 |
| RU2722370C1 (en) | 2020-05-29 |
| EP3487748A1 (en) | 2019-05-29 |
| WO2018050502A1 (en) | 2018-03-22 |
| US11299185B2 (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2017327430B2 (en) | Monitoring infrastructure facilities by means of geo-clustering | |
| CN101607565B (en) | Ground on-line monitoring device and ground on-line monitoring method for steel rail cracks | |
| AU2006202620B2 (en) | Methods and computer program product for monitoring integrity of a railroad train | |
| US10196078B2 (en) | Diagnostic system for a rail vehicle | |
| CN102887159B (en) | Method and device for railway vehicle tracking and planned reporting | |
| US9533626B2 (en) | Method and system for determining the availability of a lane for a guided vehicle | |
| CN104933869A (en) | Anti-noise type satellite positioning data-based method for identifying vehicle violation behaviors | |
| AU2021269349B2 (en) | Visual diagnostic system for railroad network | |
| US10501100B2 (en) | Route examining system | |
| CN105151084B (en) | Equipment for secondary rail detection system and the signal system comprising the equipment | |
| EP3623202A1 (en) | Method for detecting anomalies in an electric traffic system and monitoring system for detecting anomalies in an electric traffic system | |
| US20220204061A1 (en) | Examining system and method | |
| CN104260761A (en) | An orbital tracking method | |
| US20170151970A1 (en) | Diagnostic System for a Rail Vehicle | |
| CN104200659A (en) | Method for judging traffic illegal behaviors of key vehicle not running in regulation line | |
| US6763290B2 (en) | Cab signal quality detecting and reporting system and method | |
| EP3799589B1 (en) | Self organizing cyber rail-cop | |
| CN110712666A (en) | Train running distance monitoring system and method | |
| CN106896799B (en) | A kind of locomotive inspection and repair management method | |
| CN109910956B (en) | Method and system for representing and tracking train number window | |
| CN114872762B (en) | Method, device, equipment and storage medium for diagnosing and analyzing safety of railway train-ground transmission information | |
| CN116461572A (en) | Tracking method and device | |
| CN109941317A (en) | The method for tracking the not vehicle equipped with wireless device of mileometer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| FGA | Letters patent sealed or granted (standard patent) |